{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/connecting-certified-and-adversarial-training","title":"Connecting Certified and Adversarial Training","arxiv_id":null,"date":"2023-09-21","proceeding":"NeurIPS 2023 11","authors":[],"abstract":"Training certifiably robust neural networks remains a notoriously hard problem.\nWhile adversarial training optimizes under-approximations of the worst-case loss, which leads to insufficient regularization for certification, sound certified training methods, optimize loose over-approximations, leading to over-regularization and poor (standard) accuracy.\nIn this work, we propose TAPS, an (unsound) certified training method that combines IBP and PGD training to optimize more precise, although not necessarily sound, worst-case loss approximations, reducing over-regularization and increasing certified and standard accuracies.\nEmpirically, TAPS achieves a new state-of-the-art in many settings, e.g., reaching a certified accuracy of $22$% on TinyImageNet for $\\ell_\\infty$-perturbations with radius $\\epsilon=1/255$. We make our implementation and networks public at https://github.com/eth-sri/taps.Submission Number: 11952","url_abs":"https://openreview.net/forum?id=T2lM4ohRwb","url_pdf":"https://openreview.net/pdf?id=T2lM4ohRwb","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"connecting-certified-and-adversarial-training","repo_url":"https://github.com/eth-sri/taps","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}